Show a meat proxy.
an MIT researcher built a realtime LLM vector steering tool and itβs the coolest thing Iβve seen someone build in a very long time.
this is so brilliant. the primary use case I see this realistically used for is long form writing tasks. some might find it controversial, considering it plays into llm-generated writing. however in my opinion it kind of solves for some amount of the tension around the issue by making the process multiplayer in a new way. the human and the AI become collaborators, sort of.
idk this sh*t is so cool though, man.
(@ far__behind on instagram)
15
I've owned ology.se for years. Suddenly everyone wants an ontology.
Most of what gets that name is a list of what exists. The -ology was meant to be the rules: what holds, and why.
A glossary tells an agent what a customer is. It doesn't stop it deleting one.
2
25
What an agent cannot call, it cannot do. On rules that something other than the model holds:
github.com/jonasmaandiwallinβ¦
1
14
Nobody writes the exam after reading the answers.
βAcceptance tests that define βdoneββ is the right job. Ours are written from the spec, by an agent that never sees the code. A test written from the code passes the code, bugs included.
Tobi Lütke (@tobi), Shopify CEO, at Vercel Ship SF: "we are now all verification engineers. We are building harnesses, we are building acceptance tests, and we are building⦠verifiables."
When agents write the code, the work moves to the checks:
β harnesses that make agent output repeatable
β acceptance tests that define "done"
β anything a machine can verify without a dev squinting at a diff
Full fireside with @rauchg in the reply π
1
1
15
Independence is what separates a verification from a second draft.
github.com/jonasmaandiwallinβ¦
6
I set out to build with AI agents. I ended up also writing the rules to check theyβd built the right thing: Governed Agentic Engineering.
Then I came across a German profession, nearly a century old, that shows the same problem in a different light.
Nobody walks into a bank branch to check their balance anymore.
The bank didn't die. The branch did.
Your web app is the branch.
I came to the conclusion that most SaaS should become an MCP server.
weβre getting the economics of AI software backwards. A lot of AI startups are building their own chat interfaces, agents, and workflows, essentially reselling tokens from the big labs at low to negative gross margins.
What if SaaS companies did the opposite?
Take HR software. Instead of building an AI assistant, become the best MCP server for HR. Expose tools to:
- Benchmark salaries against proprietary market data
- Run compensation reviews and calculate pay equity
- Model salary increases against a departmentβs budget
- Recommend promotions based on company policies
- Update employee compensation in the HRIS
- Manage approvals, permissions, and audit trails
Let ChatGPT, Claude, or Copilot handle the conversation, reasoning, and orchestration. Let the customer pay for the tokens.
The SaaS company keeps the valuable stuff: proprietary data, integrations, business logic, permissions, compliance, and the system of record.
You still charge a SaaS subscription, but youβre no longer paying to generate every answer. You can ship faster, with fewer engineers, and potentially restore software-like gross margins.
The next generation of SaaS might not have much of a UI at all. Just an incredibly good MCP server.
1
20
Everyoneβs asking which model made this.
Nobodyβs asking who decided it needed Kipling.
(Danny Boyle did.)
1
1
32
Every editor knows the difference between βmake it betterβ and βcut it to 800 words.β
Only one of them ends.
βWould the best team in the world ship this?β is the first kind. Now give it to an agent that never sleeps.
PS: hoarding isnβt remembering.
Making the most AI pilled company is the whole game:
1. make a second brain. one folder of markdown files on how you think, write and decide (obsidian)
2. talk to it. voice notes all day (wispr), and an agent files every fact, story and decision
3. make a company brain. customers, calls, numbers, pricing, playbooks, past decisions and why you made them
4. record every call and meeting (granola). the transcripts go straight into the brain
5. keep a facts file. true things about you and the company that agents are allowed to say. this kills made-up claims
6. keep a voice file. your 50 best posts, 20 you hate, and the words you never use
7. put all of it in git (github) so every change has a history
8. write one instruction file at the top (CLAUDE.md or AGENTS.md). read these files before any task, never overwrite, always date
9. give agents memory across sessions so they stop starting from zero (claude-mem, mem0)
10. pipe every data source into one warehouse your agents can query (airbyte β clickhouse). ads, analytics, CRM, payments
11. feed it data nobody else has. it's the only part a competitor can't download
the skills
12. don't start from zero. install the good ones first (anthropics/skills, obra/superpowers, mattpocock/skills, addyosmani/agent-skills)
13. grab the marketing ones too (coreyhaines31/marketingskills, cody schneider's graphed skills for static ads and UGC, boringmarketing dot com skills)
14. map every workflow in the company and rank them by money made or saved
15. do each one once while talking out loud, and record it
16. have an agent turn the recording into a skill. when to use it, the steps, the checks, the mistakes to avoid
17. one skill per job. small and boring beats one giant prompt
18. connect your tools with MCPs so agents can act and not only advise (gmail, slack, stripe, linear, notion, posthog, supabase)
19. give agents a browser (browser-use, vercel agent-browser, claude in chrome)
20. give agents a computer of their own for the tools with no API (vercel agent-desktop, orgo)
21. give your best skills away in public. it's the new lead magnet
the agents
22. run an orchestrator that never turns off (grok bot, openclaw, hermes). it manages one agent per project, and each of those runs its own sub-agents
23. use coding agents for the building (claude code, codex, cursor, t3, antigravity)
24. wrap them in a harness so they plan, test and remember (ECC, superpowers)
25. manage the whole fleet in one place (paperclip). every agent gets a job, a budget and a log
26. put the skills on triggers (n8n, scheduled tasks). daily, weekly, on every new lead, on every cancellation
27. route your models (openrouter). the expensive one plans and checks (fable 5.2, gemini 4 carbon), the cheap ones do the volume
28. cut the token bill. shorter outputs, smaller tool results (caveman)
29. run a local model for the data that can't leave your machine (gemma 4)
30. track cost per job. if a job costs more than it earns, fix it or kill it
the factory
31. build the line. spec agent β builder agents in parallel (git worktrees) β test agent β reviewer agent β deploy (vercel, railway)
32. design goes through the same line (paper MCP), and a skill strips out anything that looks AI made (unslop)
33. every annoying task in the company becomes an internal tool by the end of the day
34. every customer request becomes a pull request before a human reads it (tstack for the PR workflow)
35. reviewer agents with a named bar. "would the best team in the world ship this?" reject until the answer is yes
36. keep 50 real cases with the right answer. rerun them every time a new model drops and switch to the winner
37. humans approve, own the outcome and talk to customers. that's the 10% you keep
the loop
38. every finished job writes back to the brain. what worked, what failed, what to stop doing
39. support tickets, analytics and social comments flow in every night
40. every friday an agent rewrites the playbooks from the week's results, and you approve the diff
41. every month, rank everything by profit per human hour. kill one thing and double one thing
the growth
42. research with agents before you spend a dollar (perplexity API, last30days skill)
43. outbound runs itself. find the leads, enrich, verify, send (apollo, million verifier, instantly, phantombuster)
44. send prospects finished work in place of a pitch
45. ads run on a loop. an agent writes the creative, publishes through the facebook ads API, kills the losers and scales the winners
46. agents make the creative too. images (nano banana), video (heygen, fal), voice (elevenlabs), music (lyria 3.5, suno)
47. turn every finished job into content. the story, the number, the prompt
48. every customer makes the brain smarter for the next one. that's your network effect
49. once it works, point it at a new niche. same agents, new context
The models are the same for everyone but your context is the only part that's yours.
Acquire as much of it as you can, as fast as you can.
Build loops like this.
This is the whole game, happy playing.
2
18
A free-form log is easy to write and impossible to count. On what a system should remember when its agents forget:
github.com/jonasmaandiwallinβ¦
12
A loop that nobody designed stops when itβs tired, not when itβs done. Five parts, a bound and an exit:
github.com/jonasmaandiwallinβ¦
9
Same account. Different vibe.
Been using this place since 2009. Yesterday I deleted about 3,000 posts. Some were great, many arenβt relevant anymore and most are just a different me.
From here on Iβm mostly going to post about agentic engineering and building with AI agents. Along with the ideas, disciplines and weird intersections that come with it.
Strategy, marketing and branding content isnβt going anywhere though.
Reset done. Letβs see what comes next.
39









